b9718

ggml-org/llama.cppb9718Jun 19, 2026by github-actions[bot]same day as b9717

What changed since b9717

low risk

Server slot selection is consolidated into a single get_available_slot function, with no functional behavior change.

Improvements

  • Slot selection logic is merged into one get_available_slot call, absorbing the former get_slot_by_id path.
  • The LCP similarity check is preserved for explicit slot-id requests, so prompt cache updates still work as before.
  • The server code is simpler and easier to maintain, with less duplicated selection logic.

Upgrade notes

This is an internal server refactor with no config, API, or CLI changes; existing deployments should behave identically. The only change from b9717 is the slot-selection consolidation, so no migration steps are needed. The Power10 Q8/Q4 MMA K-tail support from b9717 remains unchanged.

Analyzed Oct 24, 2026

Upgrading?

Release notes summary

Refactors the server's slot selection logic to consolidate functions, improving code maintainability while preserving LCP similarity checks.

Key Highlights

  • Consolidated slot selection into get_available_slot
  • Absorbed get_slot_by_id logic
  • Maintains LCP similarity check for prompt cache updates

New Features

  • Server slot selection refactoring

Release Notes (excerpt)

<details open> server : consolidate slot selection into get_available_slot (#24755) Absorb get_slot_by_id logic into get_available_slot so slot selection is handled by a single function call. When a specific slot id is requested, the LCP similarity check still runs to enable proper prompt cache updates. Assisted-by: pi:llama.cpp/Qwen3.6-27B </details> **macOS/iOS:** - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) - iOS XCFramework…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories